Merge branch 'locking-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull locking updates from Ingo Molnar:
 "Just a handful of changes in this cycle: an ARM64 performance
  optimization, a comment fix and a debug output fix"

* 'locking-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
  locking/osq: Use optimized spinning loop for arm64
  locking/qspinlock: Fix inaccessible URL of MCS lock paper
  locking/lockdep: Fix lockdep_stats indentation problem

arch/arm64/include/asm/spinlock.h

@@ -11,4 +11,13 @@
 /* See include/linux/spinlock.h */
 #define smp_mb__after_spinlock()	smp_mb()
 
+/*
+ * Changing this will break osq_lock() thanks to the call inside
+ * smp_cond_load_relaxed().
+ *
+ * See:
+ * https://lore.kernel.org/lkml/20200110100612.GC2827@hirez.programming.kicks-ass.net
+ */
+#define vcpu_is_preempted(cpu)	false
+
 #endif /* __ASM_SPINLOCK_H */

kernel/locking/lockdep_proc.c

@@ -286,9 +286,9 @@ static int lockdep_stats_show(struct seq_file *m, void *v)
 	seq_printf(m, " stack-trace entries:           %11lu [max: %lu]\n",
 			nr_stack_trace_entries, MAX_STACK_TRACE_ENTRIES);
 #if defined(CONFIG_TRACE_IRQFLAGS) && defined(CONFIG_PROVE_LOCKING)
-	seq_printf(m, " number of stack traces:        %llu\n",
+	seq_printf(m, " number of stack traces:        %11llu\n",
 		   lockdep_stack_trace_count());
-	seq_printf(m, " number of stack hash chains:   %llu\n",
+	seq_printf(m, " number of stack hash chains:   %11llu\n",
 		   lockdep_stack_hash_count());
 #endif
 	seq_printf(m, " combined max dependencies:     %11u\n",

kernel/locking/osq_lock.c

@@ -134,20 +134,17 @@ bool osq_lock(struct optimistic_spin_queue *lock)
 	 * cmpxchg in an attempt to undo our queueing.
 	 */
 
-	while (!READ_ONCE(node->locked)) {
 	/*
-		 * If we need to reschedule bail... so we can block.
-		 * Use vcpu_is_preempted() to avoid waiting for a preempted
-		 * lock holder:
+	 * Wait to acquire the lock or cancelation. Note that need_resched()
+	 * will come with an IPI, which will wake smp_cond_load_relaxed() if it
+	 * is implemented with a monitor-wait. vcpu_is_preempted() relies on
+	 * polling, be careful.
 	 */
-		if (need_resched() || vcpu_is_preempted(node_cpu(node->prev)))
-			goto unqueue;
-
-		cpu_relax();
-	}
+	if (smp_cond_load_relaxed(&node->locked, VAL || need_resched() ||
+				  vcpu_is_preempted(node_cpu(node->prev))))
 		return true;
 
-unqueue:
+	/* unqueue */
 	/*
 	 * Step - A  -- stabilize @prev
 	 *

kernel/locking/qspinlock.c

@@ -31,14 +31,15 @@
 /*
  * The basic principle of a queue-based spinlock can best be understood
  * by studying a classic queue-based spinlock implementation called the
- * MCS lock. The paper below provides a good description for this kind
- * of lock.
+ * MCS lock. A copy of the original MCS lock paper ("Algorithms for Scalable
+ * Synchronization on Shared-Memory Multiprocessors by Mellor-Crummey and
+ * Scott") is available at
  *
- * http://www.cise.ufl.edu/tr/DOC/REP-1992-71.pdf
+ * https://bugzilla.kernel.org/show_bug.cgi?id=206115
  *
- * This queued spinlock implementation is based on the MCS lock, however to make
- * it fit the 4 bytes we assume spinlock_t to be, and preserve its existing
- * API, we must modify it somehow.
+ * This queued spinlock implementation is based on the MCS lock, however to
+ * make it fit the 4 bytes we assume spinlock_t to be, and preserve its
+ * existing API, we must modify it somehow.
  *
  * In particular; where the traditional MCS lock consists of a tail pointer
  * (8 bytes) and needs the next pointer (another 8 bytes) of its own node to